Van Yüzüncü Yıl University Research Information System
Not a member yet
65114 research outputs found
Sort by
Exploring the relationship between health professionals' artificial intelligence literacy and their attitudes toward artificial intelligence.
No full textYurtlarda Barınan Öğrencilerin Depresyon Anksiyete ve Stres Düzeylerinin Kategorik Temel Bileşenler Analizi ile İncelenmesi: Van Örneği
No full text
Effects of Artificial Hydrothermal Aging on Crush Boxes Made from Glass, Carbon and Aramid Fiber-Reinforced Hybrid Composites
No full textVehicle crush boxes are one of the safety elements used in vehicles to minimize damage that may occur during an accident. The task of crush boxes is to absorb the energy which is generated during an accident. In this study, peak force, energy absorption and specific energy absorption values of cylindrical composite crush boxes, to which 0.25% and 0.50% graphene was added, were experimentally investigated with hydrothermal aging. The composite crush boxes were produced with vacuum infusion method. Glass, aramid and carbon fibers and their hybridizations were used as fibers. During hybridization, the winding order of the fibers was changed from inside to outside. The parameters for hydrothermal aging were selected as 500 h and 1000 h at 60 °C. The highest energy absorption value was obtained in the carbon fiber-reinforced sample CFRPG1H2 with 0.25% graphene-added epoxy resin matrix, aged for 1000 h. The lowest peak strength was observed in the aramid fiber-reinforced sample AFRPG2H2 with 0.50% graphene-added epoxy resin matrix, hydrothermally aged for 1000 h. It was observed that increasing the graphene addition rate reduced the negative effects on aging. It was determined that increasing the graphene ratio by 0.25% had an effect on aging.</p
Morpho-Genetic Variability in Phytochemical Composition and Essential Oils of Three Common<i> Lavandula</i> Species Cultivated in Van, Türkiye
No full textBackground: Lavandula sp. is a valuable plant species as ornamental plant with beautiful inflorescence and aromatic plant with high yield of essential oil. Lavender is mostly produced in Europe, the Middle East, Asia, Northern Africa, France and Bulgaria. Most varieties of lavender are known for their sedative properties and have historically been used to treat diabetes, depression and headaches. Chemical composition and the existence of phenolic compounds may be related to these biological properties. Aim: This study aims to compare morpho-genetic variability in total phenolics, flavonoids, antioxidants and essential oils of three Lavandula species cultivated under identical conditions. As a result of the study, total ash, dry matter, phenolic profile and mineral content of both leaf and inflorescence is clarified. Results: Both inflorescence and leaves L. intermedia has highest flavonoid content value (8.76 and 11.26 mg QE/100 g) for the study. Total antioxidant activity ranged for inflorescence 83.92 to 167.94 µmol TE/g and 75.64 to 135.48 µmol TE/g for leaves. Total phenolic content value (198.29 and 208.92 mg GAE/g) for both inflorescence and leaves obtained from L. dentata. Essential oil yield (v/w) of L. angustifolia found 7.31%, L. intermedia 4.92% and L. dentata 3.92%. Linalool were the predominant essential oil constituents in both L. angustifolia (50.04%) and L. intermedia (48.69%), whereas 1,8-cineole were (82.66%) major constituents in L. dentata. Conclusion: L. angustifolia were more productive in terms of essential oil content and also mineral content for some elements except heavy metals. For phenolic compound, while L. dentata shows higher results with total flavonoid and phenolic content, L. intermedia shows greater total antioxidant activity
Development of a machine learning model to predict the expanded disability status scale in multiple sclerosis patients
No full textObjective: The assessment of disability in multiple sclerosis (MS) patients is crucial for treatment decisions and prognosis estimation. The Expanded Disability Status Scale (EDSS) provides a standardized way to quantify disability in MS. However, predicting EDSS scores can be challenging due to the complex and heterogeneous nature of the disease. Machine learning techniques offer a promising approach to predict EDSS scores based on various patient characteristics. Methods: 231 people with MS (pwMS) who had an assessment of physical, psychosocial, and cognitive functions in three timelines (baseline (T0), first year (T1), and second year (T2)) were enrolled. The dataset used for the study consists of 126 features. Feature selection was based on feature saliency and correlation analysis. Three machine learning models —XGBoost, Random Forest, and Linear Regression —were trained on the selected features. Hyperparameter tuning was also carried out on the models. Model performance was evaluated using standard evaluation metrics, including MAE, MSE, and R². Results: The Machine Learning model based on the XGBoost algorithm performed best in predicting EDSS scores (T2). The MAE value obtained with the XGBoost model is 0.2361, the MSE value is 0.2408, and the R2 value is 0.9705. These results indicate that XGBoost's predictive ability on the current dataset is promising. Conclusion: Our study demonstrates the feasibility of using machine learning techniques to predict EDSS scores in MS patients. The developed models show promising performance and have the potential to enhance clinical decision-making and patient management in MS care
A prospective comparison of supine and prone percutaneous nephrolithotomy techniques in obese patients.
No full textARTIFICIAL INTELLIGENCE-BASED APPROACHES TO FIGHT CYBER BULLYING
No full textCyberbullying has become an important social problem with the spread of digital technologies.Social media, messaging applications and online platforms pave the way for the easy spread ofnegative interactions between individuals. In this study, the definition of cyberbullying, itseffects, detection methods and approaches to combating current technologies are discussed ina multidimensional manner. In the light of domestic and foreign studies in the literature, textmining and natural language processing (NLP) techniques developed for the analysis ofcyberbullying content, especially in the Turkish language, have been examined in detail. In thiscontext; keyword-based methods, sentiment analysis, machine learning algorithms, deeplearning models (CNN, LSTM, BERT) and social network analysis have been comparativelyevaluated.The study emphasizes that cyberbullying occurs not only through textual content but alsothrough visual, video and user interactions and draws attention to the importance of detectionsystems to be developed with the integration of multiple data types. In addition, it has beenemphasized that contextual analysis and preprocessing steps are decisive for success in additiveand low-resource languages such as Turkish. Although deep learning models have been shownto achieve high accuracy rates, issues such as data diversity and ethical data sharing are stillfundamental problems that need to be solved. As a result, early warning systems, algorithmsthat take cultural context into account, and real-time analysis capabilities should be developedto prevent cyberbullying.</p